Road recognition with a neural network

Mackeown, W.P.J.; Greenway, Phil; Thomas, Barry; Wright, W.A.

doi:10.1016/0952-1976(94)90021-3

Cited by 9 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work [11] has demonstrated a neural network approach to region classification. The work used a set of features based on internal properties of a region: colour, brightness, texture, topological properties (e.g., Euler number and hollowness), shape information (e.g., compactness and multi-scale boundary descriptors based on curvature extreina), and a set of local contextual features defined in terms of properties of pairwise combinations of a region and each of its four largest [4,Ki], such features were avoided in order to provide a more general solution.…”

Section: Methodsmentioning

confidence: 99%

“…More recently, statistical approaches to outdoor scene analysis based on region classification have been demonstrated [16,7,11]. The method described in [11] used a set of features based on properties of a region such as colour, brightness, texture, shape, topologieal properties, etc.…”

Section: Introductionmentioning

confidence: 99%

“…The method described in [11] used a set of features based on properties of a region such as colour, brightness, texture, shape, topologieal properties, etc. The system achieved a mean classification accuracy of 80.3% per image by area on a model of ideal segmentation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Interpretation of Outdoor Scenes.

Campbell¹,

Mackeown²,

Thomas

et al. 1995

Procedings of the British Machine Vision Conference 1995

View full text Add to dashboard Cite

This paper describes recent work on a neural network approach to outdoor scene interpretation. The results of evaluating a range of automatic region-based segmentation techniques based on a new segmentation quality metric are presented. The optimal technique is used to segment images of natural outdoor scenes. A powerful set of features designed for outdoor scene analysis is extracted from regions in the segmented images and used to train a neural network to recognise eleven different classes of objects, including sky, road, building and vegetation. The system is tested on a large number of images which have been hand-labelled to provide ground-truth segmentations and interpretations. This fully automated system achieves an impressive mean classification accuracy of 81.4% per image on unseen data, and runs in approximately 1 CPU minute on a Sun SPARCstation 20.

show abstract

Section: Methodsmentioning

confidence: 99%